Semi-supervised Word Sense Disambiguation Using Example Similarity Graph

Abstract

Word Sense Disambiguation (WSD) is a well-known problem in the natural language processing. In recent years, there has been increasing interest in applying neural net-works and machine learning techniques to solve WSD problems. However, these previ-ous supervised approaches often suffer from the lack of manually sense-tagged exam-ples. In this paper, to solve these problems, we propose a semi-supervised WSD method using graph embeddings based learning method in order to make effective use of labeled and unlabeled examples. The results of the experiments show that the proposed method performs better than the previous semi-supervised WSD method. Moreover, the graph structure between examples is effective for WSD and it is effective to utilize a graph structure obtained by fine-tuning BERT in the proposed method.